Observatório de previsões: metodologias e avaliação de modelos de projeção de inflação / RP


Submissões Recentes

Agora exibindo 1 - 4 de 4
  • Item
    Forecasting Industrial Production Index by its aggregated or disaggregated data? Evidence from one important emerging market
    (2019) Mendonça, Diogo de Prince; Marçal, Emerson Fernandes; Pereira, Pedro L. Valls
    Our work aims to address if the use of disaggregate data helps to forecasting industrial production index. We use Brazilian industrial production data and we investigate if disaggregate information improves the accuracy of the forecasts. We use a a number of recent econometric techniques such as the weighted lag adaptative least absolute shrinkage and selection operator (WLadaLASSO) methodology, the exponential smoothing (selecting the most appropriate model) and Autometrics algorithm to model both aggregates and disagregates. As far as we known this is the novelty of the work. We run a a forecasting exercise from one up to 12 months ahead for Brazilian industrial production. Our full sample covers the period from January of 2002 to August of 2017. Our results suggest that modeling disaggregate data better using exponential smoothing model provides the best performance for 1 up to 7 months ahead for Brazilian industrial production using mean square error as a metric and Autometrics algorithm provides better forecast for 8 up to 12 months but it is not clear whether aggregate or disagregate data is the best choice given that they are both part of the final set of good predictions.
  • Item
    Automated model selection with applications to Brazilian industrial production index
    (2019-10-23) Rocha, Jordano Vieira; Pereira, Pedro L. Valls
    Brazilian Industrial Production Index undergoes different methodological updates and periods of high inflation over time, which prompts researchers to avoid using too long industrial production series. We analyze how performance of different models in forecasting the Brazilian IndustrialProduction Index one-step ahead is influenced by the use of samples of different lengths. Relative performance of these models is also assessed. Results show that most models benefitfrom expanding the estimation sample beginning at least up to 1993:12. Autometrics lag selection with impulse dummy saturation forecasting performance is improved almost monotonically with sample size. Forestimation starting inJanuary 1975 and 1985, predictions fromAutometricswith impulse dummy saturation and the average of forecasts are statistically more accurate than those from the benchmark AR model. However, the average of predictions performs better in the first half of the forecast horizon and Autometrics performs better in the second half.
  • Item
    Does the private database help to explain Brazilian inflation?
    (2019-01) Marçal, Emerson Fernandes; Pereira, Pedro L. Valls; Mendonça, Diogo de Prince
    The large dimension of variables as regressors requires a reduction in the number of variables, which we do in this paper through the factorial model. This method is useful if the variables are collinear, as is our case. We aim to synthesize information from Brazilian Institute of Economics (IBRE)’s public and private databases to evaluate if there is an additional gain from the private database to explain the Brazilian inflation index, the broad consumer price index (IPCA). We analyze the monthly period between 2000 and 2018. After we extract factor, we select which factors are relevant regressors to explain inflation with the Autometrics algorithm. Our result is that the factors extracted from the public database bring gains to explain inflation in relation to an autoregressive model. However, the use of factors tied to the private database still leads to explanatory gains for inflation. We have been able to explain about 75% of the inflation variations with the use of the factors extracted from the private and public databases.
  • Item
    Forecasting large covariance matrices: comparing autometrics and LASSOVAR
    (2019) Cunha, Ronan; Kock, Anders Bredahl; Pereira, Pedro L. Valls
    This study aims to compare the performance of two well known automatic model selection algorithms, Autometrics (Hendry and Krolzig, 1999; Doornik, 2009), LASSOVAR and adaptive LASSOVAR (Callot et al., 2017) for modelling and forecasting monthly covariance matrices. To do so, we compose a database with daily information for 30 Brazilian stocks, which yields 465 unique entries, from July/2009 to December/2017. We apply three forecasting error measures, the model confidence set (Hansen et al., 2011) and Giacomini and White (2006) conditional test in the comparison. We also calculate the economic value for each of the forecasting strategy through a portfolio selec- tion exercise. The results show that the individual models are not able to beat the benchmark, the random walk, but a weighted combination of them is able to increase precision up to 13%. The portfolio selection exercises find that there are economic gains for using automatic model selection techniques to model and forecast the covariance matrices. Specifically, under short-selling constraint, Autometrics VAR(1) with dummy saturation delivers the highest Sharpe-ratio and economic value. When the investor is able to short-sell, ei- ther Autometrics VAR(1) with dummy saturation or adaptive Lasso VAR(1) is preferable. This final choice depend on the risk aversion of the investor. If he is less risk-averse, he prefers the former, while the latter becomes his choice if his risk-aversion sensitivity increases.